Controllable Sentence Simplification - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Controllable Sentence Simplification

Résumé

Text simplification aims at making a text easier to read and understand by simplifying grammar and structure while keeping the underlying information identical. It is often considered an all-purpose generic task where the same simplification is suitable for all; however multiple audiences can benefit from simplified text in different ways. We adapt a discrete parametrization mechanism that provides explicit control on simplification systems based on Sequence-to-Sequence models. As a result, users can condition the simplifications returned by a model on attributes such as length, amount of paraphrasing, lexical complexity and syntactic complexity. We also show that carefully chosen values of these attributes allow out-of-the-box Sequence-to-Sequence models to outperform their standard counterparts on simplification benchmarks. Our model, which we call ACCESS (as shorthand for AudienCe-CEntric Sentence Simplification), establishes the state of the art at 41.87 SARI on the WikiLarge test set, a +1.42 improvement over the best previously reported score.
Fichier principal
Vignette du fichier
LREC_2020___Controllable_Sentence_Simplification.pdf (2.14 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02678214 , version 1 (31-05-2020)

Identifiants

  • HAL Id : hal-02678214 , version 1

Citer

Louis Martin, Éric Villemonte de La Clergerie, Benoît Sagot, Antoine Bordes. Controllable Sentence Simplification. LREC 2020 - 12th Language Resources and Evaluation Conference, May 2020, Marseille, France. ⟨hal-02678214⟩
115 Consultations
342 Téléchargements

Partager

Gmail Facebook X LinkedIn More